pcre2: Update to upstream version 10.42 (take two)

Changelog: https://github.com/PCRE2Project/pcre2/blob/pcre2-10.42/ChangeLog

This fixes support for RISC-V architectures in the sljit library, so we
enable the module's compilation for `rv64` too.

Author: akien-mga

modules/regex/config.py

@@ -1,5 +1,5 @@
 def can_build(env, platform):
-    return not env["arch"].startswith("rv")
+    return True
 
 
 def configure(env):

modules/regex/regex.cpp

@@ -40,7 +40,9 @@ static void *_regex_malloc(PCRE2_SIZE size, void *user) {
 }
 
 static void _regex_free(void *ptr, void *user) {
-	memfree(ptr);
+	if (ptr) {
+		memfree(ptr);
+	}
 }
 
 int RegExMatch::_find(const Variant &p_name) const {

thirdparty/README.md

@@ -597,7 +597,7 @@ Exclude:
 ## pcre2
 
 - Upstream: http://www.pcre.org
-- Version: 10.40 (3103b8f20a3b9944b177e812fde29fbfb8b90558, 2022)
+- Version: 10.42 (52c08847921a324c804cabf2814549f50bce1265, 2022)
 - License: BSD-3-Clause
 
 Files extracted from upstream source:

thirdparty/pcre2/src/config.h

@@ -236,7 +236,7 @@ sure both macros are undefined; an emulation function will then be used. */
 #define PACKAGE_NAME "PCRE2"
 
 /* Define to the full name and version of this package. */
-#define PACKAGE_STRING "PCRE2 10.40"
+#define PACKAGE_STRING "PCRE2 10.42"
 
 /* Define to the one symbol short name of this package. */
 #define PACKAGE_TARNAME "pcre2"
@@ -245,7 +245,7 @@ sure both macros are undefined; an emulation function will then be used. */
 #define PACKAGE_URL ""
 
 /* Define to the version of this package. */
-#define PACKAGE_VERSION "10.40"
+#define PACKAGE_VERSION "10.42"
 
 /* The value of PARENS_NEST_LIMIT specifies the maximum depth of nested
    parentheses (of any kind) in a pattern. This limits the amount of system
@@ -438,7 +438,13 @@ sure both macros are undefined; an emulation function will then be used. */
 #endif
 
 /* Version number of package */
-#define VERSION "10.40"
+#define VERSION "10.42"
+
+/* Number of bits in a file offset, on hosts where this is settable. */
+/* #undef _FILE_OFFSET_BITS */
+
+/* Define for large files, on AIX-style hosts. */
+/* #undef _LARGE_FILES */
 
 /* Define to empty if `const' does not conform to ANSI C. */
 /* #undef const */

thirdparty/pcre2/src/pcre2.h

@@ -42,9 +42,9 @@ POSSIBILITY OF SUCH DAMAGE.
 /* The current PCRE version information. */
 
 #define PCRE2_MAJOR           10
-#define PCRE2_MINOR           40
+#define PCRE2_MINOR           42
 #define PCRE2_PRERELEASE      
-#define PCRE2_DATE            2022-04-14
+#define PCRE2_DATE            2022-12-11
 
 /* When an application links to a PCRE DLL in Windows, the symbols that are
 imported have to be identified as such. When building PCRE2, the appropriate
@@ -572,19 +572,19 @@ PCRE2_EXP_DECL int PCRE2_CALL_CONVENTION pcre2_config(uint32_t, void *);
 /* Functions for manipulating contexts. */
 
 #define PCRE2_GENERAL_CONTEXT_FUNCTIONS \
-PCRE2_EXP_DECL pcre2_general_context PCRE2_CALL_CONVENTION \
-  *pcre2_general_context_copy(pcre2_general_context *); \
-PCRE2_EXP_DECL pcre2_general_context PCRE2_CALL_CONVENTION \
-  *pcre2_general_context_create(void *(*)(PCRE2_SIZE, void *), \
+PCRE2_EXP_DECL pcre2_general_context *PCRE2_CALL_CONVENTION \
+  pcre2_general_context_copy(pcre2_general_context *); \
+PCRE2_EXP_DECL pcre2_general_context *PCRE2_CALL_CONVENTION \
+  pcre2_general_context_create(void *(*)(PCRE2_SIZE, void *), \
     void (*)(void *, void *), void *); \
 PCRE2_EXP_DECL void PCRE2_CALL_CONVENTION \
   pcre2_general_context_free(pcre2_general_context *);
 
 #define PCRE2_COMPILE_CONTEXT_FUNCTIONS \
-PCRE2_EXP_DECL pcre2_compile_context PCRE2_CALL_CONVENTION \
-  *pcre2_compile_context_copy(pcre2_compile_context *); \
-PCRE2_EXP_DECL pcre2_compile_context PCRE2_CALL_CONVENTION \
-  *pcre2_compile_context_create(pcre2_general_context *);\
+PCRE2_EXP_DECL pcre2_compile_context *PCRE2_CALL_CONVENTION \
+  pcre2_compile_context_copy(pcre2_compile_context *); \
+PCRE2_EXP_DECL pcre2_compile_context *PCRE2_CALL_CONVENTION \
+  pcre2_compile_context_create(pcre2_general_context *);\
 PCRE2_EXP_DECL void PCRE2_CALL_CONVENTION \
   pcre2_compile_context_free(pcre2_compile_context *); \
 PCRE2_EXP_DECL int PCRE2_CALL_CONVENTION \
@@ -604,10 +604,10 @@ PCRE2_EXP_DECL int PCRE2_CALL_CONVENTION \
     int (*)(uint32_t, void *), void *);
 
 #define PCRE2_MATCH_CONTEXT_FUNCTIONS \
-PCRE2_EXP_DECL pcre2_match_context PCRE2_CALL_CONVENTION \
-  *pcre2_match_context_copy(pcre2_match_context *); \
-PCRE2_EXP_DECL pcre2_match_context PCRE2_CALL_CONVENTION \
-  *pcre2_match_context_create(pcre2_general_context *); \
+PCRE2_EXP_DECL pcre2_match_context *PCRE2_CALL_CONVENTION \
+  pcre2_match_context_copy(pcre2_match_context *); \
+PCRE2_EXP_DECL pcre2_match_context *PCRE2_CALL_CONVENTION \
+  pcre2_match_context_create(pcre2_general_context *); \
 PCRE2_EXP_DECL void PCRE2_CALL_CONVENTION \
   pcre2_match_context_free(pcre2_match_context *); \
 PCRE2_EXP_DECL int PCRE2_CALL_CONVENTION \
@@ -631,10 +631,10 @@ PCRE2_EXP_DECL int PCRE2_CALL_CONVENTION \
     void *(*)(PCRE2_SIZE, void *), void (*)(void *, void *), void *);
 
 #define PCRE2_CONVERT_CONTEXT_FUNCTIONS \
-PCRE2_EXP_DECL pcre2_convert_context PCRE2_CALL_CONVENTION \
-  *pcre2_convert_context_copy(pcre2_convert_context *); \
-PCRE2_EXP_DECL pcre2_convert_context PCRE2_CALL_CONVENTION \
-  *pcre2_convert_context_create(pcre2_general_context *); \
+PCRE2_EXP_DECL pcre2_convert_context *PCRE2_CALL_CONVENTION \
+  pcre2_convert_context_copy(pcre2_convert_context *); \
+PCRE2_EXP_DECL pcre2_convert_context *PCRE2_CALL_CONVENTION \
+  pcre2_convert_context_create(pcre2_general_context *); \
 PCRE2_EXP_DECL void PCRE2_CALL_CONVENTION \
   pcre2_convert_context_free(pcre2_convert_context *); \
 PCRE2_EXP_DECL int PCRE2_CALL_CONVENTION \
@@ -646,15 +646,15 @@ PCRE2_EXP_DECL int PCRE2_CALL_CONVENTION \
 /* Functions concerned with compiling a pattern to PCRE internal code. */
 
 #define PCRE2_COMPILE_FUNCTIONS \
-PCRE2_EXP_DECL pcre2_code PCRE2_CALL_CONVENTION \
-  *pcre2_compile(PCRE2_SPTR, PCRE2_SIZE, uint32_t, int *, PCRE2_SIZE *, \
+PCRE2_EXP_DECL pcre2_code *PCRE2_CALL_CONVENTION \
+  pcre2_compile(PCRE2_SPTR, PCRE2_SIZE, uint32_t, int *, PCRE2_SIZE *, \
     pcre2_compile_context *); \
 PCRE2_EXP_DECL void PCRE2_CALL_CONVENTION \
   pcre2_code_free(pcre2_code *); \
-PCRE2_EXP_DECL pcre2_code PCRE2_CALL_CONVENTION \
-  *pcre2_code_copy(const pcre2_code *); \
-PCRE2_EXP_DECL pcre2_code PCRE2_CALL_CONVENTION \
-  *pcre2_code_copy_with_tables(const pcre2_code *);
+PCRE2_EXP_DECL pcre2_code *PCRE2_CALL_CONVENTION \
+  pcre2_code_copy(const pcre2_code *); \
+PCRE2_EXP_DECL pcre2_code *PCRE2_CALL_CONVENTION \
+  pcre2_code_copy_with_tables(const pcre2_code *);
 
 
 /* Functions that give information about a compiled pattern. */
@@ -670,10 +670,10 @@ PCRE2_EXP_DECL int PCRE2_CALL_CONVENTION \
 /* Functions for running a match and inspecting the result. */
 
 #define PCRE2_MATCH_FUNCTIONS \
-PCRE2_EXP_DECL pcre2_match_data PCRE2_CALL_CONVENTION \
-  *pcre2_match_data_create(uint32_t, pcre2_general_context *); \
-PCRE2_EXP_DECL pcre2_match_data PCRE2_CALL_CONVENTION \
-  *pcre2_match_data_create_from_pattern(const pcre2_code *, \
+PCRE2_EXP_DECL pcre2_match_data *PCRE2_CALL_CONVENTION \
+  pcre2_match_data_create(uint32_t, pcre2_general_context *); \
+PCRE2_EXP_DECL pcre2_match_data *PCRE2_CALL_CONVENTION \
+  pcre2_match_data_create_from_pattern(const pcre2_code *, \
     pcre2_general_context *); \
 PCRE2_EXP_DECL int PCRE2_CALL_CONVENTION \
   pcre2_dfa_match(const pcre2_code *, PCRE2_SPTR, PCRE2_SIZE, PCRE2_SIZE, \
@@ -689,8 +689,8 @@ PCRE2_EXP_DECL PCRE2_SIZE PCRE2_CALL_CONVENTION \
   pcre2_get_match_data_size(pcre2_match_data *); \
 PCRE2_EXP_DECL uint32_t PCRE2_CALL_CONVENTION \
   pcre2_get_ovector_count(pcre2_match_data *); \
-PCRE2_EXP_DECL PCRE2_SIZE PCRE2_CALL_CONVENTION \
-  *pcre2_get_ovector_pointer(pcre2_match_data *); \
+PCRE2_EXP_DECL PCRE2_SIZE *PCRE2_CALL_CONVENTION \
+  pcre2_get_ovector_pointer(pcre2_match_data *); \
 PCRE2_EXP_DECL PCRE2_SIZE PCRE2_CALL_CONVENTION \
   pcre2_get_startchar(pcre2_match_data *);
 
@@ -770,8 +770,8 @@ PCRE2_EXP_DECL int PCRE2_CALL_CONVENTION \
     uint32_t, pcre2_match_data *, pcre2_match_context *); \
 PCRE2_EXP_DECL void PCRE2_CALL_CONVENTION \
   pcre2_jit_free_unused_memory(pcre2_general_context *); \
-PCRE2_EXP_DECL pcre2_jit_stack PCRE2_CALL_CONVENTION \
-  *pcre2_jit_stack_create(PCRE2_SIZE, PCRE2_SIZE, pcre2_general_context *); \
+PCRE2_EXP_DECL pcre2_jit_stack *PCRE2_CALL_CONVENTION \
+  pcre2_jit_stack_create(PCRE2_SIZE, PCRE2_SIZE, pcre2_general_context *); \
 PCRE2_EXP_DECL void PCRE2_CALL_CONVENTION \
   pcre2_jit_stack_assign(pcre2_match_context *, pcre2_jit_callback, void *); \
 PCRE2_EXP_DECL void PCRE2_CALL_CONVENTION \
@@ -783,8 +783,8 @@ PCRE2_EXP_DECL void PCRE2_CALL_CONVENTION \
 #define PCRE2_OTHER_FUNCTIONS \
 PCRE2_EXP_DECL int PCRE2_CALL_CONVENTION \
   pcre2_get_error_message(int, PCRE2_UCHAR *, PCRE2_SIZE); \
-PCRE2_EXP_DECL const uint8_t PCRE2_CALL_CONVENTION \
-  *pcre2_maketables(pcre2_general_context *); \
+PCRE2_EXP_DECL const uint8_t *PCRE2_CALL_CONVENTION \
+  pcre2_maketables(pcre2_general_context *); \
 PCRE2_EXP_DECL void PCRE2_CALL_CONVENTION \
   pcre2_maketables_free(pcre2_general_context *, const uint8_t *);
 

thirdparty/pcre2/src/pcre2_compile.c

@@ -1266,8 +1266,10 @@ PCRE2_SIZE* ref_count;
 
 if (code != NULL)
   {
+#ifdef SUPPORT_JIT
   if (code->executable_jit != NULL)
     PRIV(jit_free)(code->executable_jit, &code->memctl);
+#endif
 
   if ((code->flags & PCRE2_DEREF_TABLES) != 0)
     {
@@ -2687,7 +2689,7 @@ if ((options & PCRE2_EXTENDED_MORE) != 0) options |= PCRE2_EXTENDED;
 while (ptr < ptrend)
   {
   int prev_expect_cond_assert;
-  uint32_t min_repeat, max_repeat;
+  uint32_t min_repeat = 0, max_repeat = 0;
   uint32_t set, unset, *optset;
   uint32_t terminator;
   uint32_t prev_meta_quantifier;
@@ -8552,7 +8554,7 @@ do {
             op == OP_SCBRA || op == OP_SCBRAPOS)
      {
      int n = GET2(scode, 1+LINK_SIZE);
-     int new_map = bracket_map | ((n < 32)? (1u << n) : 1);
+     unsigned int new_map = bracket_map | ((n < 32)? (1u << n) : 1);
      if (!is_startline(scode, new_map, cb, atomcount, inassert)) return FALSE;
      }
 
@@ -10620,4 +10622,10 @@ re = NULL;
 goto EXIT;
 }
 
+/* These #undefs are here to enable unity builds with CMake. */
+
+#undef NLBLOCK /* Block containing newline information */
+#undef PSSTART /* Field containing processed string start */
+#undef PSEND   /* Field containing processed string end */
+
 /* End of pcre2_compile.c */

thirdparty/pcre2/src/pcre2_context.c

@@ -7,7 +7,7 @@ and semantics are as close as possible to those of the Perl 5 language.
 
                        Written by Philip Hazel
      Original API code Copyright (c) 1997-2012 University of Cambridge
-          New API code Copyright (c) 2016-2018 University of Cambridge
+          New API code Copyright (c) 2016-2022 University of Cambridge
 
 -----------------------------------------------------------------------------
 Redistribution and use in source and binary forms, with or without
@@ -443,8 +443,11 @@ mcontext->offset_limit = limit;
 return 0;
 }
 
-/* This function became obsolete at release 10.30. It is kept as a synonym for
-backwards compatibility. */
+/* These functions became obsolete at release 10.30. The first is kept as a
+synonym for backwards compatibility. The second now does nothing. Exclude both
+from coverage reports. */
+
+/* LCOV_EXCL_START */
 
 PCRE2_EXP_DEFN int PCRE2_CALL_CONVENTION
 pcre2_set_recursion_limit(pcre2_match_context *mcontext, uint32_t limit)
@@ -464,6 +467,9 @@ pcre2_set_recursion_memory_management(pcre2_match_context *mcontext,
 return 0;
 }
 
+/* LCOV_EXCL_STOP */
+
+
 /* ------------ Convert context ------------ */
 
 PCRE2_EXP_DEFN int PCRE2_CALL_CONVENTION

thirdparty/pcre2/src/pcre2_convert.c

@@ -7,7 +7,7 @@ and semantics are as close as possible to those of the Perl 5 language.
 
                        Written by Philip Hazel
      Original API code Copyright (c) 1997-2012 University of Cambridge
-          New API code Copyright (c) 2016-2018 University of Cambridge
+          New API code Copyright (c) 2016-2022 University of Cambridge
 
 -----------------------------------------------------------------------------
 Redistribution and use in source and binary forms, with or without
@@ -65,9 +65,8 @@ POSSIBILITY OF SUCH DAMAGE.
 #define STR_QUERY_s STR_LEFT_PARENTHESIS STR_QUESTION_MARK STR_s STR_RIGHT_PARENTHESIS
 #define STR_STAR_NUL STR_LEFT_PARENTHESIS STR_ASTERISK STR_N STR_U STR_L STR_RIGHT_PARENTHESIS
 
-/* States for range and POSIX processing */
+/* States for POSIX processing */
 
-enum { RANGE_NOT_STARTED, RANGE_STARTING, RANGE_STARTED };
 enum { POSIX_START_REGEX, POSIX_ANCHORED, POSIX_NOT_BRACKET,
        POSIX_CLASS_NOT_STARTED, POSIX_CLASS_STARTING, POSIX_CLASS_STARTED };
 

thirdparty/pcre2/src/pcre2_dfa_match.c

@@ -350,7 +350,7 @@ Returns:            the return from the callout
 */
 
 static int
-do_callout(PCRE2_SPTR code, PCRE2_SIZE *offsets, PCRE2_SPTR current_subject,
+do_callout_dfa(PCRE2_SPTR code, PCRE2_SIZE *offsets, PCRE2_SPTR current_subject,
   PCRE2_SPTR ptr, dfa_match_block *mb, PCRE2_SIZE extracode,
   PCRE2_SIZE *lengthptr)
 {
@@ -2799,7 +2799,7 @@ for (;;)
             || code[LINK_SIZE + 1] == OP_CALLOUT_STR)
           {
           PCRE2_SIZE callout_length;
-          rrc = do_callout(code, offsets, current_subject, ptr, mb,
+          rrc = do_callout_dfa(code, offsets, current_subject, ptr, mb,
             1 + LINK_SIZE, &callout_length);
           if (rrc < 0) return rrc;                 /* Abandon */
           if (rrc > 0) break;                      /* Fail this thread */
@@ -3196,7 +3196,7 @@ for (;;)
       case OP_CALLOUT_STR:
         {
         PCRE2_SIZE callout_length;
-        rrc = do_callout(code, offsets, current_subject, ptr, mb, 0,
+        rrc = do_callout_dfa(code, offsets, current_subject, ptr, mb, 0,
           &callout_length);
         if (rrc < 0) return rrc;   /* Abandon */
         if (rrc == 0)
@@ -4057,4 +4057,10 @@ while (rws->next != NULL)
 return rc;
 }
 
+/* These #undefs are here to enable unity builds with CMake. */
+
+#undef NLBLOCK /* Block containing newline information */
+#undef PSSTART /* Field containing processed string start */
+#undef PSEND   /* Field containing processed string end */
+
 /* End of pcre2_dfa_match.c */

thirdparty/pcre2/src/pcre2_internal.h

@@ -220,18 +220,17 @@ not rely on this. */
 
 #define COMPILE_ERROR_BASE 100
 
-/* The initial frames vector for remembering backtracking points in
-pcre2_match() is allocated on the system stack, of this size (bytes). The size
-must be a multiple of sizeof(PCRE2_SPTR) in all environments, so making it a
-multiple of 8 is best. Typical frame sizes are a few hundred bytes (it depends
-on the number of capturing parentheses) so 20KiB handles quite a few frames. A
-larger vector on the heap is obtained for patterns that need more frames. The
-maximum size of this can be limited. */
+/* The initial frames vector for remembering pcre2_match() backtracking points
+is allocated on the heap, of this size (bytes) or ten times the frame size if
+larger, unless the heap limit is smaller. Typical frame sizes are a few hundred
+bytes (it depends on the number of capturing parentheses) so 20KiB handles
+quite a few frames. A larger vector on the heap is obtained for matches that
+need more frames, subject to the heap limit. */
 
 #define START_FRAMES_SIZE 20480
 
-/* Similarly, for DFA matching, an initial internal workspace vector is
-allocated on the stack. */
+/* For DFA matching, an initial internal workspace vector is allocated on the
+stack. The heap is used only if this turns out to be too small. */
 
 #define DFA_START_RWS_SIZE 30720